1 (* Copyright (C) 2004, HELM Team.
3 * This file is part of HELM, an Hypertextual, Electronic
4 * Library of Mathematics, developed at the Computer Science
5 * Department, University of Bologna, Italy.
7 * HELM is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation; either version 2
10 * of the License, or (at your option) any later version.
12 * HELM is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with HELM; if not, write to the Free Software
19 * Foundation, Inc., 59 Temple Place - Suite 330, Boston,
22 * For details, see the HELM World-Wide-Web page,
23 * http://helm.cs.unibo.it/
26 exception Error of int * int * string
28 exception Not_an_extended_ident
30 let regexp alpha = [ 'a' - 'z' 'A' - 'Z' ]
31 let regexp digit = [ '0' - '9' ]
32 let regexp blank = [ ' ' '\t' '\n' ]
33 let regexp paren = [ '(' '[' '{' ')' ']' '}' ]
34 let regexp implicit = '?'
35 let regexp symbol_char =
36 [^ 'a' - 'z' 'A' - 'Z' '0' - '9' ' ' '\t' '\n' '\\' '(' '[' '{' ')' ']' '}' ]
38 let regexp blanks = blank+
39 let regexp num = digit+
40 let regexp tex_token = '\\' alpha+
41 let regexp symbol = symbol_char+
42 let regexp ident_cont = alpha | num | '_' | '\''
43 let regexp ident_cont' = ident_cont | tex_token
44 let regexp ident = (alpha ident_cont*) | ('_' ident_cont+)
45 let regexp ident' = ((alpha | tex_token) ident_cont'*) | ('_' ident_cont'+)
46 let regexp meta = implicit num
47 let regexp qstring = '"' [^ '"']* '"'
49 (* schema *) (* path *) (* ext *) (* xpointer *)
50 ("cic:/" | "theory:/") ident ('/' ident)* ('.' ident)+ ('#' num ('/' num)*)?
51 (* let regexp catchall = .* *)
53 let keywords = Hashtbl.create 17
55 List.iter (fun keyword -> Hashtbl.add keywords keyword ("", keyword))
56 [ "Prop"; "Type"; "Set"; "let"; "Let"; "rec"; "using"; "match"; "with";
59 let error lexbuf msg =
60 raise (Error (Ulexing.lexeme_start lexbuf, Ulexing.lexeme_end lexbuf, msg))
61 let error_at_end lexbuf msg =
62 raise (Error (Ulexing.lexeme_end lexbuf, Ulexing.lexeme_end lexbuf, msg))
64 let return lexbuf token =
66 { Lexing.pos_fname = ""; Lexing.pos_lnum = -1; Lexing.pos_bol = -1;
67 Lexing.pos_cnum = Ulexing.lexeme_start lexbuf }
70 { flocation_begin with Lexing.pos_cnum = Ulexing.lexeme_end lexbuf }
72 (token, (flocation_begin, flocation_end))
75 let parse_ext_ident ident =
76 let len = String.length ident in
77 let buf = Buffer.create len in
78 let in_tex_token = ref false in
79 let tex_token = Buffer.create 10 in
81 for i = 0 to len - 1 do
83 | '\' when not !in_tex_token ->
87 with Invalid_argument -> assert false
89 let rec token' = lexer
92 let ident = parse_ext_ident (Ulexing.utf8_lexeme lexbuf) in
93 return lexbuf ("IDENT'", ident)
94 with Not_an_extended_ident ->
95 Ulexing.rollback lexbuf;
98 Ulexing.rollback lexbuf;
103 let rec token = lexer
104 | blanks -> token lexbuf
105 | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
107 let lexeme = Ulexing.utf8_lexeme lexbuf in
109 return lexbuf (Hashtbl.find keywords lexeme)
110 with Not_found -> return lexbuf ("IDENT", lexeme))
111 | num -> return lexbuf ("NUM", Ulexing.utf8_lexeme lexbuf)
112 | paren -> return lexbuf ("PAREN", Ulexing.utf8_lexeme lexbuf)
113 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
114 | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
116 let lexeme = Ulexing.utf8_lexeme lexbuf in
117 let s = String.sub lexeme 1 (String.length lexeme - 2) in
118 return lexbuf ("QSTRING", s)
119 | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
122 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
125 return lexbuf ("SYMBOL", Utf8Macro.expand macro)
126 with Utf8Macro.Macro_not_found _ ->
127 return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
128 | eof -> return lexbuf ("EOI", "")
129 | _ -> error lexbuf "Invalid character"
131 let tok_func stream =
132 let lexbuf = Ulexing.from_utf8_stream stream in
133 Token.make_stream_and_flocation
138 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
139 | Ulexing.InvalidCodepoint i -> error_at_end lexbuf "Invalid code point")
143 Token.tok_func = tok_func;
144 Token.tok_using = (fun _ -> ());
145 Token.tok_removing = (fun _ -> ());
146 Token.tok_match = Token.default_match;
147 Token.tok_text = Token.lexer_text;
148 Token.tok_comm = None;